Lately a simple idea has been spreading across the developer internet: Rust is an ideal language for AI agents to program in. I think the real reason has less to do with raw speed and more to do with trust. When an agent writes Rust, everything around it works in its favor. The type system, the borrow checker and the compiler act as a built-in reviewer that checks every step the agent takes.
Recently, while developing my AI agent library, agentai, I introduced a new CI pipeline to run examples against various models for each pull request. This process ensures that all elements of the library work correctly with each new release. I started by running these tests using GitHub Models, primarily for convenience (as they are already integrated) and to enable external contributors to use the same test suite in the same environment.
Recently, I was working on the AI_Devs course, which aims to teach how AI agents work and how to create them. I completed all the exercises using the Rust programming language, and during that time, I started developing a common library to group code that could be shared across different subprojects for the course. After finishing the entire course, one file — agent.rs — stood out to me as particularly useful in most of the exercises. This was the initial implementation of my library, AgentAI.
AgentAI is a Rust library designed to simplify the creation of AI agents. It leverages the GenAI library to interface with a wide range of popular Large Language Models (LLMs), making it versatile and powerful. Written in Rust, AgentAI benefits from strong static typing and robust error handling, ensuring more reliable and maintainable code. Whether you’re developing simple or complex AI agents, AgentAI provides a streamlined and efficient development process.